Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 14554
    Prev
    Next
    INDEX
    Explanations

    text related to the action of shooting or shooting-related contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to the action of shooting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    $$$$
    -0.82
    STEP
    -0.81
    ebook
    -0.79
    States
    -0.76
    BuyableInstoreAndOnline
    -0.75
    roe
    -0.70
    REG
    -0.70
    Eng
    -0.70
     streng
    -0.69
    chid
    -0.69
    POSITIVE LOGITS
     shoot
    1.00
    outs
    0.87
     Shoot
    0.86
     shoots
    0.84
     shooting
    0.84
     weddings
    0.80
     outs
    0.72
    ters
    0.72
     Shooting
    0.71
    shoot
    0.71
    Activations Density 0.020%

    No Known Activations